解决opencv检测矩形框无法显示中文的现象

解决opencv检测矩形框无法显示中文的现象

前段时间做过一个人脸识别的项目，刚开始做的时候发现了一个问题，就是当检测到目标人脸时，它的检测矩形框内只能出现英文，而当改成中文时会出现乱码的现象，所以在很多场景下，会极大的影响用户体验，当检测出人脸时，无法显示中文人名。

参考代码展示

这是主文件的所有代码

import cv2
import os
import numpy as np
from net.mtcnn import mtcnn
import utils.utils as utils
from net.inception import InceptionResNetV1


class face_rec():
    def __init__(self):
        # 创建mtcnn对象
        # 检测图片中的人脸
        self.mtcnn_model = mtcnn()
        # 门限函数
        self.threshold = [0.5, 0.8, 0.9]

        # 载入facenet
        # 将检测到的人脸转化为128维的向量
        self.facenet_model = InceptionResNetV1()
        # model.summary()
        model_path = './model_data/facenet_keras.h5'
        self.facenet_model.load_weights(model_path)

        # -----------------------------------------------#
        #   对数据库中的人脸进行编码
        #   known_face_encodings中存储的是编码后的人脸
        #   known_face_names为人脸的名字
        # -----------------------------------------------#
        face_list = os.listdir("face_dataset")

        self.known_face_encodings = []

        self.known_face_names = []

        for face in face_list:
            name = face.split(".")[0]

            img = cv2.imread("./face_dataset/" + face)
            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

            # 检测人脸
            rectangles = self.mtcnn_model.detectFace(img, self.threshold)

            # 转化成正方形
            rectangles = utils.rect2square(np.array(rectangles))
            # facenet要传入一个160x160的图片
            rectangle = rectangles[0]
            # 记下他们的landmark
            landmark = (np.reshape(rectangle[5:15], (5, 2)) - np.array([int(rectangle[0]), int(rectangle[1])])) / (
                        rectangle[3] - rectangle[1]) * 160

            crop_img = img[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
            crop_img = cv2.resize(crop_img, (160, 160))

            new_img, _ = utils.Alignment_1(crop_img, landmark)

            new_img = np.expand_dims(new_img, 0)
            # 将检测到的人脸传入到facenet的模型中，实现128维特征向量的提取
            face_encoding = utils.calc_128_vec(self.facenet_model, new_img)

            self.known_face_encodings.append(face_encoding)
            self.known_face_names.append(name)

    def recognize(self, draw):
        # -----------------------------------------------#
        #   人脸识别
        #   先定位，再进行数据库匹配
        # -----------------------------------------------#
        height, width, _ = np.shape(draw)
        draw_rgb = cv2.cvtColor(draw, cv2.COLOR_BGR2RGB)

        # 检测人脸
        rectangles = self.mtcnn_model.detectFace(draw_rgb, self.threshold)
        print(np.shape(rectangles))
        if len(rectangles) == 0:
            return

        # 转化成正方形
        rectangles = utils.rect2square(np.array(rectangles, dtype=np.int32))
        rectangles[:, 0] = np.clip(rectangles[:, 0], 0, width)
        rectangles[:, 1] = np.clip(rectangles[:, 1], 0, height)
        rectangles[:, 2] = np.clip(rectangles[:, 2], 0, width)
        rectangles[:, 3] = np.clip(rectangles[:, 3], 0, height)
        # -----------------------------------------------#
        #   对检测到的人脸进行编码
        # -----------------------------------------------#
        face_encodings = []
        for rectangle in rectangles:
            # 获取landmark在小图中的坐标
            landmark = (np.reshape(rectangle[5:15], (5, 2)) - np.array([int(rectangle[0]), int(rectangle[1])])) / (
                        rectangle[3] - rectangle[1]) * 160
            # 截取图像
            crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
            crop_img = cv2.resize(crop_img, (160, 160))
            # 对齐
            new_img, _ = utils.Alignment_1(crop_img, landmark)
            new_img = np.expand_dims(new_img, 0)
            # 利用facenet_model计算128维特征向量
            face_encoding = utils.calc_128_vec(self.facenet_model, new_img)
            face_encodings.append(face_encoding)

        face_names = []
        for face_encoding in face_encodings:
            # 取出一张脸并与数据库中所有的人脸进行对比，计算得分
            matches = utils.compare_faces(self.known_face_encodings, face_encoding, tolerance=0.9)
            name = "Unknown"
            # 找出距离最近的人脸
            face_distances = utils.face_distance(self.known_face_encodings, face_encoding)
            # 取出这个最近人脸的评分
            best_match_index = np.argmin(face_distances)
            if matches[best_match_index]:
                name = self.known_face_names[best_match_index]
            face_names.append(name)

        rectangles = rectangles[:, 0:4]
        # -----------------------------------------------#
        #   画框~!~
        # -----------------------------------------------#
        for (left, top, right, bottom), name in zip(rectangles, face_names):
            cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)

            font = cv2.FONT_HERSHEY_SIMPLEX
            cv2.putText(draw, name, (left, bottom - 15), font, 0.75, (255, 255, 255), 2)
        return draw


if __name__ == "__main__":

    dududu = face_rec()
    video_capture = cv2.VideoCapture(1)

    while True:
        ret, draw = video_capture.read()
        dududu.recognize(draw)
        cv2.imshow('Video', draw)
        if cv2.waitKey(20) & 0xFF == ord('q'):
            break

    video_capture.release()
    cv2.destroyAllWindows()

修改后代码

import cv2
import os
import numpy as np
from net.mtcnn import mtcnn
import utils.utils as utils
from net.inception import InceptionResNetV1
from PIL import Image,ImageDraw,ImageFont


def change_cv2_draw(image,name,local,sizes,colour):

    if (isinstance(image, np.ndarray)):  #判断是否OpenCV图片类型
        pil_img = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
    draw1 = ImageDraw.Draw(pil_img)  # 图片上打印
    font = ImageFont.truetype("SIMLI.TTF",sizes, encoding="utf-8")
    draw1.text(local, name, colour, font=font)
    #PIL转opencv
    image = cv2.cvtColor(np.array(pil_img), cv2.COLOR_RGB2BGR)
    return image

class face_rec():
    def __init__(self):
        # 创建mtcnn对象
        # 检测图片中的人脸
        self.mtcnn_model = mtcnn()
        # 门限函数
        self.threshold = [0.5,0.8,0.9]

        # 载入facenet
        # 将检测到的人脸转化为128维的向量
        self.facenet_model = InceptionResNetV1()
        # model.summary()
        model_path = './model_data/facenet_keras.h5'
        self.facenet_model.load_weights(model_path)

        #-----------------------------------------------#
        #   对数据库中的人脸进行编码
        #   known_face_encodings中存储的是编码后的人脸
        #   known_face_names为人脸的名字
        #-----------------------------------------------#
        face_list = os.listdir("face_dataset")

        self.known_face_encodings=[]

        self.known_face_names=[]

        for face in face_list:
            name = face.split(".")[0]

            #img = cv2.imread("./face_dataset/"+face)
            #img = cv2.imdecode(np.fromfile("./face_dataset/"+face, dtype=np.uint8), -1)
            img=cv2.imdecode(np.fromfile("./face_dataset/"+face, dtype=np.uint8),cv2.IMREAD_COLOR)
            img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)

            # 检测人脸
            rectangles = self.mtcnn_model.detectFace(img, self.threshold)

            # 转化成正方形
            rectangles = utils.rect2square(np.array(rectangles))
            # facenet要传入一个160x160的图片
            rectangle = rectangles[0]
            # 记下他们的landmark
            landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*160

            crop_img = img[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
            crop_img = cv2.resize(crop_img,(160,160))

            new_img,_ = utils.Alignment_1(crop_img,landmark)

            new_img = np.expand_dims(new_img,0)
            # 将检测到的人脸传入到facenet的模型中，实现128维特征向量的提取
            face_encoding = utils.calc_128_vec(self.facenet_model,new_img)

            self.known_face_encodings.append(face_encoding)
            self.known_face_names.append(name)


    def recognize(self,draw):
        #-----------------------------------------------#
        #   人脸识别
        #   先定位，再进行数据库匹配
        #-----------------------------------------------#
        height,width,_ = np.shape(draw)
        draw_rgb = cv2.cvtColor(draw,cv2.COLOR_BGR2RGB)
        # 检测人脸
        rectangles = self.mtcnn_model.detectFace(draw_rgb, self.threshold)

        if len(rectangles)==0:
            return

        # 转化成正方形
        rectangles = utils.rect2square(np.array(rectangles,dtype=np.int32))
        rectangles[:,0] = np.clip(rectangles[:,0],0,width)
        rectangles[:,1] = np.clip(rectangles[:,1],0,height)
        rectangles[:,2] = np.clip(rectangles[:,2],0,width)
        rectangles[:,3] = np.clip(rectangles[:,3],0,height)
        #-----------------------------------------------#
        #   对检测到的人脸进行编码
        #-----------------------------------------------#
        face_encodings = []
        for rectangle in rectangles:
            landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*160

            crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
            crop_img = cv2.resize(crop_img,(160,160))

            new_img,_ = utils.Alignment_1(crop_img,landmark)
            new_img = np.expand_dims(new_img,0)

            face_encoding = utils.calc_128_vec(self.facenet_model,new_img)
            face_encodings.append(face_encoding)

        face_names = []
        for face_encoding in face_encodings:
            # 取出一张脸并与数据库中所有的人脸进行对比，计算得分
            matches = utils.compare_faces(self.known_face_encodings, face_encoding, tolerance = 0.9)
            name = "我不认识你"
            # 找出距离最近的人脸
            face_distances = utils.face_distance(self.known_face_encodings, face_encoding)
            # 取出这个最近人脸的评分
            best_match_index = np.argmin(face_distances)
            if matches[best_match_index]:
                name = self.known_face_names[best_match_index]
            face_names.append(name)

        rectangles = rectangles[:,0:4]
        #-----------------------------------------------#
        #   画框~!~
        #-----------------------------------------------#
        for (left, top, right, bottom), name in zip(rectangles, face_names):
            cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)
            #font=ImageFont.truetype('simhei.ttf',10,encoding="utf-8")
            #font = cv2.FONT_HERSHEY_SIMPLEX
            draw=change_cv2_draw(draw, name, (left, bottom - 30), 25, (255, 0, 0))
            #cv2.putText(draw, name, (left, bottom - 15), font, 0.75, (255, 255, 255), 2)
            cv2.imshow("video", draw)
            return draw

if __name__ == "__main__":

    dududu = face_rec()
    video_capture = cv2.VideoCapture(0)

    while True:
        ret, draw = video_capture.read()
        dududu.recognize(draw)
        #cv2.imshow('Video', draw)
        if cv2.waitKey(20) & 0xFF == ord('q'):
            break

    video_capture.release()
    cv2.destroyAllWindows()

主要修改点

1 解决路径存在中文情况下图片读取
由于我的数据库中图片名称很多都是由中文命名的，放的是一些同学的人脸，嘻嘻！ 然后再读取的报错中会报错，不能读取中文路径。
我把原来的：

img = cv2.imread("./face_dataset/"+face)

OpenCV下读取英文路径，改成了：

img=cv2.imdecode(np.fromfile("./face_dataset/"+face, dtype=np.uint8),cv2.IMREAD_COLOR)

当然，这个也是可以的：

img = cv2.imdecode(np.fromfile("./face_dataset/"+face, dtype=np.uint8), -1)

有好几种方法，看看自己喜欢用哪种，当然这样修改后，不但可以读取中文路径的图片，全是英文路径的同样适用。
2 opencv与PIL的转换
主要思路是，先将原来的cv2格式转化为PIL格式，由于PIL库支持中文输入，所以转化为PIL图片后写上中文，再将PIL图片转为cv2格式。
先定义了一个转化函数：

def change_cv2_draw(image,name,local,sizes,colour):

    if (isinstance(image, np.ndarray)):  #判断是否OpenCV图片类型
        pil_img = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
    draw1 = ImageDraw.Draw(pil_img)  # 图片上打印
    font = ImageFont.truetype("SIMLI.TTF",sizes, encoding="utf-8")
    draw1.text(local, name, colour, font=font)
    image = cv2.cvtColor(np.array(pil_img), cv2.COLOR_RGB2BGR)
    return image

调用函数：

draw=change_cv2_draw(draw, name, (left, bottom - 30), 25, (255, 0, 0))

补充

可能细心的同学发现了：

        for (left, top, right, bottom), name in zip(rectangles, face_names):
            cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)
            #font=ImageFont.truetype('simhei.ttf',10,encoding="utf-8")
            #font = cv2.FONT_HERSHEY_SIMPLEX
            draw=change_cv2_draw(draw, name, (left, bottom - 30), 25, (255, 0, 0))
            #cv2.putText(draw, name, (left, bottom - 15), font, 0.75, (255, 255, 255), 2)
            cv2.imshow("video", draw)
            return draw

if __name__ == "__main__":

    dududu = face_rec()
    video_capture = cv2.VideoCapture(0)

    while True:
        ret, draw = video_capture.read()
        dududu.recognize(draw)
        #cv2.imshow('Video', draw)
        if cv2.waitKey(20) & 0xFF == ord('q'):
            break

    video_capture.release()
    cv2.destroyAllWindows()

我把cv2.imshow(“video”, draw)从下面的主函数下改到了上面，因为当这句代码还是放在下面的时候，边框是不会出现文字的（乱码也不会出现）。还有就是，我在代码里面设置了一些参数，都是凭个人喜好，检测矩形框内的字体颜色，大小，字体都可以自己设置，只要不超过范围，还是可以玩一玩的。